Translation inference through multi-lingual word embedding similarity

• Kathrin Donandt ^[1] ; Christian Chiarcos ^[1]
  1. [1] Goethe University Frankfurt

     Goethe University Frankfurt

     Frankfurt, Alemania

     
• Localización: Proceedings of TIAD-2019 Shared Task – Translation Inference Across Dictionaries co-located with the 2nd Language, Data and Knowledge Conference (LDK 2019): Leipzig, Germany, May 20, 2019 / Jorge Gracia (ed. lit.), Besim Kabashi (ed. lit.), Ilan Kernerman (ed. lit.), 2019, págs. 42-53
• Idioma: inglés
• Enlaces
  • Texto completo (pdf)
• Resumen

  • This paper describes our contribution to the Shared Task on Translation Inference across Dictionaries (TIAD-2019). In our approach, we construct a multi-lingual word embedding space by projecting new languages in the feature space of a language for which a pretrained em- bedding model exists. We use the similarity of the word embeddings to predict candidate translations. Even if our projection methodology is rather simplistic, our system outperforms the other participating sys- tems with respect to the F1 measure for the language pairs which we predicted.